Search code examples
javac#asp.netweb-scrapingjsoup

Unable to navigate aspx pages via jsoup while scraping


I am scraping a url(http://nvsos.gov/sosentitysearch/CorpSearch.aspx) in jsoup , However I am able to scrape the first page but unable to navigate to second page.

Here is the code snippet

try
{
    string url = "http://nvsos.gov/sosentitysearch/CorpSearch.aspx";
    Connection.Response response = Jsoup.connect(url).method(Connection.Method.GET).execute();
    Document responseDocument = response.parse();

    Element eventValidation = responseDocument.select("input[name=__EVENTVALIDATION]").first();
    Element viewState = responseDocument.select("input[name=__VIEWSTATE]").first();

    //javascript:__doPostBack('ctl00$MainContent$objSearchGrid$dgCorpSearchResults$ctl54$ctl01','')
    response = Jsoup.connect(url)
    .data("__VIEWSTATE", viewState.attr("value"))
    .data("__EVENTVALIDATION", eventValidation.attr("value"))
    .data("ctl00$MainContent$txtSearchBox", "apple")  // <- search 
    .data("ctl00$MainContent$btnCorpSearch", "Search")
    .data("ctl00$MainContent$ddlCorpSortColumns", "m")
    .data("ctl00$MainContent$ddlCorpNumSortColumns", "m")
    .data("ctl00$MainContent$ddlOfficerSortColumns", "m")
    .data("ctl00$MainContent$ddlRASortColumns", "m")
    .data("ctl00$MainContent$ddlABNSortColumns", "m")
    .data("ctl00$MainContent$ddlABNSortColumns", "m")
    .data("ctl00$MainContent$rdlSortOrder", "d")
    .data("ctl00$MainContent$objSearchGrid$dgCorpSearchResults$ctl54$ctl01", "")
    .method(Connection.Method.POST)
    .followRedirects(true)
    .execute();

    Document document = response.parse(); //search results
    System.out.println(document);

}
catch (IOException e)
{
    e.printStackTrace();
}

Here .data("ctl00$MainContent$objSearchGrid$dgCorpSearchResults$ctl54$ctl01", "") is to navigate to second page but it always returns first page.


Solution

  • You may be missing some cookies. Try the code below:

    response = Jsoup.connect(url)
    .cookies(response.cookies()) // Add cookies received when fetching the first page
    .data("__VIEWSTATE", viewState.attr("value"))
    .data("__EVENTVALIDATION", eventValidation.attr("value"))
    .data("ctl00$MainContent$txtSearchBox", "apple")  // <- search 
    .data("ctl00$MainContent$btnCorpSearch", "Search")
    .data("ctl00$MainContent$ddlCorpSortColumns", "m")
    .data("ctl00$MainContent$ddlCorpNumSortColumns", "m")
    .data("ctl00$MainContent$ddlOfficerSortColumns", "m")
    .data("ctl00$MainContent$ddlRASortColumns", "m")
    .data("ctl00$MainContent$ddlABNSortColumns", "m")
    .data("ctl00$MainContent$ddlABNSortColumns", "m")
    .data("ctl00$MainContent$rdlSortOrder", "d")
    .data("ctl00$MainContent$objSearchGrid$dgCorpSearchResults$ctl54$ctl01", "")
    .method(Connection.Method.POST)
    .followRedirects(true)
    .execute();